Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    examples and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    檛
    0.43
    undering
    0.40
    Shopping
    0.38
    mobile
    0.38
    航空
    0.38
    移动
    0.37
    ｻ
    0.37
    moving
    0.36
    उंस
    0.36
    dining
    0.36
    POSITIVE LOGITS
     dataset
    0.52
    例えば
    0.50
     exemplo
    0.50
     timeframe
    0.49
     exemple
    0.47
     exemplu
    0.46
     예를
    0.46
     length
    0.46
     example
    0.45
     Zeitraum
    0.44
    Act Density 0.001%

    No Known Activations